Method for parallelism-aware wavelength-routed optical networks-on-chip design

Abstract

A method for a parallelism-aware wavelength-routed optical networks-on-chip design is proposed, which is executed by a computer, the method comprising using the computer to perform the following: providing a WRONoC netlist, design specs and design rules; performing a network construction such that potential positions of each core of a plurality of cores, a plurality of waveguides and a plurality of microring resonators (MRRs) are determined to create a topology; performing a message routing to minimize MRR type usage of the MRRs in the topology; and performing a MRR radius selection to select a radius from MRR-radius options for each MRR type in said topology based on a simulated annealing.

What is claimed is: 
     
       1. A non-transitory computer-readable medium containing instructions, which when read and executed by a computer, cause the computer to execute a method of a parallelism-aware wavelength-routed optical networks-on-chip (WRONoC) design, wherein the method comprises steps of:
 providing a WRONoC netlist, design specs and design rules stored in a memory for said computer-readable medium; 
 performing a network construction such that potential positions of each core of a plurality of cores, a plurality of waveguides and a plurality of microring resonators (MRRs) are determined to create a topology stored in said memory; 
 performing a message routing to minimize MRR type usage of said MRRs in said topology; and 
 performing a MRR radius selection to select a radius from MRR-radius options for each MRR type in said topology based on a simulated annealing. 
 
     
     
       2. The non-transitory computer-readable medium of  claim 1 , where said each core of said plurality of cores is decomposed into a sender-receiver pair. 
     
     
       3. The non-transitory computer-readable medium of  claim 2 , where said plurality of waveguides are classified into horizontal waveguides, vertical waveguides and ring-like waveguides in said network construction. 
     
     
       4. The non-transitory computer-readable medium of  claim 3 , where potential positions of said horizontal waveguides are on each core's right, allowing a signal emission from senders, potential positions of said vertical waveguides are on each core's top, allowing a signal transmission to receivers, and potential positions of said ring-like waveguides are close to a boundary of said topology, connecting said horizontal waveguides on a bottom-right and said vertical waveguides on a top-left in said network construction. 
     
     
       5. The non-transitory computer-readable medium of  claim 2 , wherein signals transmitted from an identical sender are activating different MRR types during said message routing. 
     
     
       6. The non-transitory computer-readable medium of  claim 5 , wherein signals transmitted to an identical receiver are activating different MRR types during said message routing. 
     
     
       7. The non-transitory computer-readable medium of  claim 6 , wherein said each core of said plurality of cores is occupied a unique absolute position during said message routing. 
     
     
       8. The non-transitory computer-readable medium of  claim 7 , wherein a default path has a last signal extracted from compound signal sent by its sender, and a first signal recombined to said vertical waveguide towards its receiver. 
     
     
       9. The non-transitory computer-readable medium of  claim 1 , wherein said simulated annealing is performing to replace a radius in a radius sequence with an unselected radius from said MRR-radius options. 
     
     
       10. The non-transitory computer-readable medium of  claim 9 , wherein said simulated annealing is performing to further swap two radii in said radius sequence and sort said radius sequence according to a cardinality of a resonance wavelength of each radius. 
     
     
       11. A method of a parallelism-aware wavelength-routed optical networks-on-chip (WRONoC) design, which is executed by a computer, the method comprising:
 using the computer to perform the following: 
 providing a WRONoC netlist, design specs and design rules stored in a memory for computer-readable medium; 
 performing a network construction such that potential positions of each core of a plurality of cores, a plurality of waveguides and a plurality of microring resonators (MRRs) are determined to create a topology stored in said memory; 
 performing a message routing to minimize MRR type usage of said MRRs in said topology; and 
 performing a MRR radius selection to select a radius from MRR-radius options for each MRR type in said topology based on a simulated annealing. 
 
     
     
       12. The method of  claim 11 , where said each core of said plurality of cores is decomposed into a sender-receiver pair. 
     
     
       13. The method of  claim 12 , wherein said plurality of waveguides are classified into horizontal waveguides, vertical waveguides and ring-like waveguides in said network construction. 
     
     
       14. The method of  claim 13 , wherein potential positions of said horizontal waveguides are on each core's right, allowing a signal emission from senders, potential positions of said vertical waveguides are on each core's top, allowing a signal transmission to receivers, and potential positions of said ring-like waveguides are close to a boundary of said topology, connecting said horizontal waveguides on a bottom-right and said vertical waveguides on a top-left in said network construction. 
     
     
       15. The method of  claim 12 , wherein signals transmitted from an identical sender are activating different MRR types during said message routing. 
     
     
       16. The method of  claim 15 , wherein signals transmitted to an identical receiver are activating different MRR types during said message routing. 
     
     
       17. The method of  claim 16 , wherein said each core of said plurality of cores is occupied a unique absolute position during said message routing. 
     
     
       18. The method of  claim 17 , wherein a default path has a last signal extracted from compound signal sent by its sender, and a first signal recombined to said vertical waveguide towards its receiver. 
     
     
       19. The method of  claim 11 , wherein said simulated annealing is performing to replace a radius in a radius sequence with an unselected radius from said MRR-radius options. 
     
     
       20. The method of  claim 19 , wherein said simulated annealing is performing to further swap two radii in said radius sequence and sort said radius sequence according to a cardinality of a resonance wavelength of each radius.